Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
A simple post-hoc geometric calibration method recovers lost out-of-domain capabilities and boosts in-domain performance after SFT, even on large, diverse models.
LLM agents can now dynamically curate multimodal memory on-demand, achieving optimal performance-cost-latency trade-offs by intelligently choosing between pre-computed and runtime-generated evidence.
Text-centric agentic search is out: Deep-Reporter shows how to build multimodal agents that leverage both text and visuals for grounded long-form generation.
